Instructions to use troed/Qwen3.8-27B-ASCII-Condensed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use troed/Qwen3.8-27B-ASCII-Condensed with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
# Run inference directly in the terminal:
llama cli -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
# Run inference directly in the terminal:
llama cli -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
# Run inference directly in the terminal:
./llama-cli -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Use Docker

docker model run hf.co/troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Llama new
LM Studio
Jan

vLLM

How to use troed/Qwen3.8-27B-ASCII-Condensed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "troed/Qwen3.8-27B-ASCII-Condensed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "troed/Qwen3.8-27B-ASCII-Condensed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Ollama
How to use troed/Qwen3.8-27B-ASCII-Condensed with Ollama:
```
ollama run hf.co/troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
```
Unsloth Desktop

How to use troed/Qwen3.8-27B-ASCII-Condensed with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use troed/Qwen3.8-27B-ASCII-Condensed with Docker Model Runner:
```
docker model run hf.co/troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S
```

Lemonade

How to use troed/Qwen3.8-27B-ASCII-Condensed with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Run and chat with the model

lemonade run user.Qwen3.8-27B-ASCII-Condensed-Q2_K_S

List all available models

lemonade list

Hermes Agent

How to use troed/Qwen3.8-27B-ASCII-Condensed with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use troed/Qwen3.8-27B-ASCII-Condensed with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "troed/Qwen3.8-27B-ASCII-Condensed:Q2_K_S" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

llama.cpp-adaptive-kv-streaming\ggml\src\ggml-cpu\ops.cpp:5015: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed

by aatai - opened Sep 26

Discussion

aatai

Sep 26

•

edited Sep 26

I tried this model in upstream latest and your fork:

I get this issue in both:
llama.cpp-adaptive-kv-streaming\ggml\src\ggml-cpu\ops.cpp:5015: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed

Im on a 4060ti 16GB.

==
Update: issue was with the dflash2 draft model which i downloaded from https://huggingface.co/HermiHg/Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUF instead of from here

aatai changed discussion status to closed Sep 26

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment